Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have e...Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have explored the incorporation of Transformers to augment network performance in SISR.However,the high computational cost of Transformers makes them less suitable for deployment on lightweight devices.Moreover,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel convolution.In this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel convolution.Specifically,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these features.In addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel dimensions.Experimental results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.展开更多
文摘Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have explored the incorporation of Transformers to augment network performance in SISR.However,the high computational cost of Transformers makes them less suitable for deployment on lightweight devices.Moreover,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel convolution.In this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel convolution.Specifically,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these features.In addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel dimensions.Experimental results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.
文摘为了提高牛场无人机目标跟踪算法的实时性和鲁棒性,试验以无人机跟踪牛只图像为研究对象,提出了一种基于残差累积模板的轻型孪生网络(siamese tracker with residual accumulation template, SiamRAT)目标跟踪算法,即采用轻量级卷积网络MobileNetV2为特征提取网络及以锚框比率变化为契机的模板更新机制,提高了算法的实时性;采用高置信度残差累积模板和多峰欧式距离检测模块来解决因相似牛只干扰而产生的跟踪漂移问题;最后将SiamRAT算法与SiamRPN++、SiamDW、DaSiamRPN、SiamRPN、ECO-HC算法在由无人机采集牧场牛只视频制作的测试数据集和VOT2018数据集中相同属性视频构成的测试数据集上,以平均精确度、鲁棒性及帧率(frames per second, FPS)为指标进行性能比较,并分析改进模块(包括残差累积模板、高置信度更新和峰值距离检测3个模块的改进)对SiamRAT算法的贡献。结果表明:与SiamRPN++、SiamDW、DaSiamRPN、SiamRPN、ECO-HC算法相比,SiamRAT算法鲁棒性最优,平均精确度稍有下降,但仍处于所有算法的第二位;FPS较SiamRPN++算法有了较大提升,性能较优。改进模块的SiamRAT算法的鲁棒性和FPS有了较大提升,平均精确度达到了0.909。说明SiamRAT算法能够很好地适应于牛场无人机跟踪环境。
